Abstract
Performance on a dataset is often regarded as the key criterion for assessing NLP models. I argue for a broader perspective, which emphasizes scientific explanation. I draw on a long tradition in the philosophy of science, and on the Bayesian approach to assessing scientific theories, to argue for a plurality of criteria for assessing NLP models. To illustrate these ideas, I compare some recent models of language production with each other. I conclude by asking what it would mean for institutional policies if the NLP community took these ideas onboard.- Anthology ID:
- 2023.cl-3.6
- Volume:
- Computational Linguistics, Volume 49, Issue 3 - September 2023
- Month:
- September
- Year:
- 2023
- Address:
- Cambridge, MA
- Venue:
- CL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 749–761
- Language:
- URL:
- https://aclanthology.org/2023.cl-3.6
- DOI:
- 10.1162/coli_a_00480
- Cite (ACL):
- Kees van Deemter. 2023. Dimensions of Explanatory Value in NLP Models. Computational Linguistics:749–761.
- Cite (Informal):
- Dimensions of Explanatory Value in NLP Models (van Deemter, CL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.cl-3.6.pdf